Automated lane changing is a critical feature for advanced autonomous driving systems. In recent years, reinforcement learning (RL) algorithms trained on traffic simulators yielded successful results in computing lane changing policies that strike a balance between safety, agility and compensating for traffic uncertainty. However, many RL algorithms exhibit simulator bias and policies trained on simple simulators do not generalize well to realistic traffic scenarios. In this work, we develop a data driven traffic simulator by training a generative adverserial network (GAN) on real life trajectory data. The simulator generates randomized trajectories that resembles real life traffic interactions between vehicles, which enables training the RL agent on much richer and realistic scenarios. We demonstrate through simulations that RL agents that are trained on GAN-based traffic simulator has stronger generalization capabilities compared to RL agents trained on simple rule-driven simulators.

We propose a standardized methodology for developing and evaluating use cases for quantum computers and quantum inspired methods. This methodology consists of a standardized set of questions which should be asked to determine how and indeed if, near term quantum computing can play a role in a given application. Developing such a set of questions is important because it allows different use cases to be evaluated in a fair and objective way, rather than considering each case on an ad hoc basis which could lead to an evaluation which focuses on positives of a use case, while ignoring weaknesses. To demonstrate our methodology we apply it to a concrete use case, ambulance dispatch, and find that there are some ways in which near term quantum computing could be deployed sensibly, but also demonstrate some cases ways in which its use would not be advised. The purpose of this paper is to initiate a dialogue within the community of quantum computing scientists and potential end users on what questions should be asked when developing real world use cases.

Individuality is essential in human society, which induces the division of labor and thus improves the efficiency and productivity. Similarly, it should also be the key to multi-agent cooperation. Inspired by that individuality is of being an individual separate from others, we propose a simple yet efficient method for the emergence of individuality (EOI) in multi-agent reinforcement learning (MARL). EOI learns a probabilistic classifier that predicts a probability distribution over agents given their observation and gives each agent an intrinsic reward of being correctly predicted by the classifier. The intrinsic reward encourages the agents to visit their own familiar observations, and learning the classifier by such observations makes the intrinsic reward signals stronger and the agents more identifiable. To further enhance the intrinsic reward and promote the emergence of individuality, two regularizers are proposed to increase the discriminability of the classifier. We implement EOI on top of popular MARL algorithms. Empirically, we show that EOI significantly outperforms existing methods in a variety of multi-agent cooperative scenarios.

Optimization models generally aim for efficiency by maximizing total benefit or minimizing cost. Yet a trade-off between fairness and efficiency is an important element of many practical decisions. We propose a principled and practical method for balancing these two criteria in an optimization model. Following a critical assessment of existing schemes, we define a set of social welfare functions (SWFs) that combine Rawlsian leximax fairness and utilitarianism and overcome some of the weaknesses of previous approaches. In particular, we regulate the equity/efficiency trade-off with a single parameter that has a meaningful interpretation in practical contexts. We formulate the SWFs using mixed integer constraints and sequentially maximize them subject to constraints that define the problem at hand. After providing practical step-by-step instructions for implementation, we demonstrate the method on problems of realistic size involving healthcare resource allocation and disaster preparation. The solution times are modest, ranging from a fraction of a second to 18 seconds for a given value of the trade-off parameter.

Assessment of job performance, personalized health and psychometric measures are domains where data-driven and ubiquitous computing exhibits the potential of a profound impact in the future. Existing techniques use data extracted from questionnaires, sensors (wearable, computer, etc.), or other traits, to assess well-being and cognitive attributes of individuals. However, these techniques can neither predict individual's well-being and psychological traits in a global manner nor consider the challenges associated to processing the data available, that is incomplete and noisy. In this paper, we create a benchmark for predictive analysis of individuals from a perspective that integrates: physical and physiological behavior, psychological states and traits, and job performance. We design data mining techniques as benchmark and uses real noisy and incomplete data derived from wearable sensors to predict 19 constructs based on 12 standardized well-validated tests. The study included 757 participants who were knowledge workers in organizations across the USA with varied work roles. We developed a data mining framework to extract the meaningful predictors for each of the 19 variables under consideration. Our model is the first benchmark that combines these various instrument-derived variables in a single framework to understand people's behavior by leveraging real uncurated data from wearable, mobile, and social media sources. We verify our approach experimentally using the data obtained from our longitudinal study. The results show that our framework is consistently reliable and capable of predicting the variables under study better than the baselines when prediction is restricted to the noisy, incomplete data.

We consider shared workspace scenarios with humans and robots acting to achieve independent goals, termed as parallel play. We model these as general-sum games and construct a framework that utilizes the Nash equilibrium solution concept to consider the interactive effect of both agents while planning. We find multiple Pareto-optimal equilibria in these tasks. We hypothesize that people act by choosing an equilibrium based on social norms and their personalities. To enable coordination, we infer the equilibrium online using a probabilistic model that includes these two factors and use it to select the robot's action. We apply our approach to a close-proximity pick-and-place task involving a robot and a simulated human with three potential behaviors - defensive, selfish, and norm-following. We showed that using a Bayesian approach to infer the equilibrium enables the robot to complete the task with less than half the number of collisions while also reducing the task execution time as compared to the best baseline. We also performed a study with human participants interacting either with other humans or with different robot agents and observed that our proposed approach performs similar to human-human parallel play interactions. The code is available at https://github.com/shray/bayes-nash

In this paper, we present a new reinforcement learning (RL) algorithm called Distributional Soft Actor Critic (DSAC), which exploits the distributional information of accumulated rewards to achieve better performance. Seamlessly integrating SAC (which uses entropy to encourage exploration) with a principled distributional view of the underlying objective, DSAC takes into consideration the randomness in both action and rewards, and beats the state-of-the-art baselines in several continuous control benchmarks. Moreover, with the distributional information of rewards, we propose a unified framework for risk-sensitive learning, one that goes beyond maximizing only expected accumulated rewards. Under this framework we discuss three specific risk-related metrics: percentile, mean-variance and distorted expectation. Our extensive experiments demonstrate that with distribution modeling in RL, the agent performs better for both risk-averse and risk-seeking control tasks.

Modern cyber-physical systems (CPS), such as our energy infrastructure, are becoming increasingly complex: An ever-higher share of Artificial Intelligence (AI)-based technologies use the Information and Communication Technology (ICT) facet of energy systems for operation optimization, cost efficiency, and to reach CO2 goals worldwide. At the same time, markets with increased flexibility and ever shorter trade horizons enable the multi-stakeholder situation that is emerging in this setting. These systems still form critical infrastructures that need to perform with highest reliability. However, today's CPS are becoming too complex to be analyzed in the traditional monolithic approach, where each domain, e.g., power grid and ICT as well as the energy market, are considered as separate entities while ignoring dependencies and side-effects. To achieve an overall analysis, we introduce the concept for an application of distributed artificial intelligence as a self-adaptive analysis tool that is able to analyze the dependencies between domains in CPS by attacking them. It eschews pre-configured domain knowledge, instead exploring the CPS domains for emergent risk situations and exploitable loopholes in codices, with a focus on rational market actors that exploit the system while still following the market rules.

Achieving transparency in black-box deep learning algorithms is still an open challenge. High dimensional features and decisions given by deep neural networks (NN) require new algorithms and methods to expose its mechanisms. Current state-of-the-art NN interpretation methods (e.g. Saliency maps, DeepLIFT, LIME, etc.) focus more on the direct relationship between NN outputs and inputs rather than the NN structure and operations itself. In current deep NN operations, there is uncertainty over the exact role played by neurons with fixed activation functions. In this paper, we achieve partially explainable learning model by symbolically explaining the role of activation functions (AF) under a scalable topology. This is carried out by modeling the AFs as adaptive Gaussian Processes (GP), which sit within a novel scalable NN topology, based on the Kolmogorov-Arnold Superposition Theorem (KST). In this scalable NN architecture, the AFs are generated by GP interpolation between control points and can thus be tuned during the back-propagation procedure via gradient descent. The control points act as the core enabler to both local and global adjustability of AF, where the GP interpolation constrains the intrinsic autocorrelation to avoid over-fitting. We show that there exists a trade-off between the NN's expressive power and interpretation complexity, under linear KST topology scaling. To demonstrate this, we perform a case study on a binary classification dataset of banknote authentication. By quantitatively and qualitatively investigating the mapping relationship between inputs and output, our explainable model can provide interpretation over each of the one-dimensional attributes. These early results suggest that our model has the potential to act as the final interpretation layer for deep neural networks.

In the realm of games research, Artificial General Intelligence algorithms often use score as main reward signal for learning or playing actions. However this has shown its severe limitations when the point rewards are very rare or absent until the end of the game. This paper proposes a new approach based on event logging: the game state triggers an event every time one of its features changes. These events are processed by an Event-value Function (EF) that assigns a value to a single action or a sequence. The experiments have shown that such approach can mitigate the problem of scarce point rewards and improve the AI performance. Furthermore this represents a step forward in controlling the strategy adopted by the artificial agent, by describing a much richer and controllable behavioural space through the EF. Tuned EF are able to neatly synthesise the relevance of the events in the game. Agents using an EF show more robust when playing games with several opponents.